baa-ai
/

Llama-3.1-70B-Instruct-SWAN-5bit-MLX

mixed-precision

4-bit precision

Model card Files Files and versions

Llama-3.1-70B-Instruct-SWAN-5bit-MLX / generation_config.json

Trevor Kennedy

SWAN adaptive mixed-precision quantization (5.51 avg bits, MAD bounds)

abf7841 verified 7 months ago

History Blame Contribute Delete

234 Bytes

	{
	"bos_token_id": 128000,
	"do_sample": true,
	"eos_token_id": [
	128001,
	128008,
	128009
	],
	"max_length": 131072,
	"pad_token_id": 128004,
	"temperature": 0.6,
	"top_p": 0.9,
	"transformers_version": "4.44.2"
	}